LLM EXPLORER 59,420 MODELS INDEXED

Magnum V2 123B by anthracite-org

By anthracite-org · 62 downloads
HF Repo ↗ Copy URL

Magnum V2 123B is an open-source language model by anthracite-org. Features: 123b LLM, VRAM: 207.6GB, Context: 128K, License: other, Instruction-Based, LLM Explorer Score: 0.14.

Base model:finetune:mistralai/... Base model:mistralai/mistral-l...   Chat   Conversational Dataset:anthracite-org/kalo-op... Dataset:anthracite-org/nopm cl... Dataset:doctor-shotgun/c2-sthe...   De   En   Endpoints compatible   Es   Fr   Instruct   It   Ja   Mistral   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/anthracite-org/magnum-v2-123b 

Magnum V2 123B Parameters and Internals

Model Type 
text generation
Additional Notes 
This is the sixth model in a series to replicate the prose quality of Claude 3 models, specifically Sonnet and Opus.
Supported Languages 
en (supported), fr (supported), de (supported), es (supported), it (supported), pt (supported), ru (supported), zh (supported), ja (supported)
Training Details 
Data Sources:
anthracite-org/Stheno-Data-Filtered, anthracite-org/kalo-opus-instruct-22k-no-refusal, anthracite-org/nopm_claude_writing_fixed
Methodology:
Instruct tuning with Mistral formatting
Training Time:
1.5 epochs
Hardware Used:
8x AMD Instinct™ MI300X Accelerators
Input Output 
Input Format:
Mistral formatting: [INST] USER MESSAGE[/INST]
Accepted Modalities:
text
Performance Tips:
Recommend replacing misconfigured SillyTavern presets with Context and Instruct presets.
LLM NameMagnum V2 123B
Repository 🤗https://huggingface.co/anthracite-org/magnum-v2-123b 
Base Model(s)  Mistral Large Instruct 2407   mistralai/Mistral-Large-Instruct-2407
Model Size123b
Required VRAM207.6 GB
Updated2026-08-02
Maintaineranthracite-org
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-51   4.8 GB: 2-of-51   4.9 GB: 3-of-51   4.8 GB: 4-of-51   4.8 GB: 5-of-51   4.8 GB: 6-of-51   4.9 GB: 7-of-51   4.8 GB: 8-of-51   4.8 GB: 9-of-51   4.8 GB: 10-of-51   4.9 GB: 11-of-51   4.8 GB: 12-of-51   4.8 GB: 13-of-51   4.8 GB: 14-of-51   4.9 GB: 15-of-51   4.8 GB: 16-of-51   4.8 GB: 17-of-51   4.8 GB: 18-of-51   4.9 GB: 19-of-51   4.8 GB: 20-of-51   4.8 GB: 21-of-51   4.8 GB: 22-of-51   4.9 GB: 23-of-51   4.8 GB: 24-of-51   4.8 GB: 25-of-51   4.8 GB: 26-of-51   4.9 GB: 27-of-51   4.8 GB: 28-of-51   4.8 GB: 29-of-51   4.8 GB: 30-of-51   4.9 GB: 31-of-51   4.8 GB: 32-of-51   4.8 GB: 33-of-51   4.8 GB: 34-of-51   4.9 GB: 35-of-51   4.8 GB: 36-of-51   4.8 GB: 37-of-51   4.8 GB: 38-of-51   4.9 GB: 39-of-51   4.8 GB: 40-of-51   4.8 GB: 41-of-51   4.8 GB: 42-of-51   4.9 GB: 43-of-51
Supported Languagesen fr de es it pt ru zh ja
Model ArchitectureMistralForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.43.4
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Magnum V2 123B

Best Alternatives
Context / RAM
Downloads
Likes
Behemoth ReduX 123B V1128K / 217.2 GB7014
Behemoth X 123B V2128K / 217.2 GB4732
Behemoth R1 123B V2128K / 226.4 GB1229
ML2 123B Magnum Diamond128K / 212.4 GB12613
Gigaberg Mistral Large 123B128K / 222 GB62
Cakrawala 123B128K / 222 GB64
Behemoth 123B V2128K / 221.6 GB410
Behemoth 123B V1128K / 221.6 GB644
Magnum V4 123B128K / 222 GB2233
Lumikabra 123B V0.4128K / 216.7 GB912
Note: green Score (e.g. "73.2") means that the model is better than anthracite-org/magnum-v2-123b.